Tavily MCP

CALL ANY TOOL

Run AI-optimized web searches, extract content from URLs, search for RAG context, and get direct QnA answers.

tavily_search

Web search

Run an AI-optimized web search and return relevant results with content.

Parameters

Name

Type

Required

Description

query

string

Required

Search query

search_depth

string

Optional

Search depth: basic or advanced

max_results

integer

Optional

Max results: 1-20

include_domains

array

Optional

Restrict to these domains

exclude_domains

array

Optional

Exclude these domains

tavily_search_context

Search with context

tavily_extract

Extract URL

tavily_search_qna

QnA search

Build your Agent

Drop the toolkit in, point it at the user, and your research agent can use Tavily MCP from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tavilymcp"], toolNames: ["tavily_search", "tavily_search_context", "tavily_extract"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tavilymcp"], toolNames: ["tavily_search", "tavily_search_context", "tavily_extract"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["tavilymcp"], toolNames: ["tavily_search", "tavily_search_context", "tavily_extract"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/tavilymcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Tavily MCP.

Web search

Copy the prompt

Copied

Search for [query] and return top 5 results.

Copy the prompt

Copied

What are the latest news about [topic]?

Copy the prompt

Copied

Search for recent pricing changes at [company].

Copy the prompt

Copied

Find [topic] limited to [domain.com].

Extract & research

Copy the prompt

Copied

Extract content from [URL].

Copy the prompt

Copied

Scrape [competitor pricing page URL].

Copy the prompt

Copied

Get content from these 5 URLs: [list].

Copy the prompt

Copied

Extract product features from [URL].

RAG & QnA

Copy the prompt

Copied

Search context for: what is [concept]?

Copy the prompt

Copied

Direct answer: when did [company] raise Series B?

Copy the prompt

Copied

Get relevant chunks about [topic] for embedding.

Copy the prompt

Copied

Factual answer: what is [company]'s current pricing?

SEE HOW AUTH WORKS

Users authorize Tavily MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Tavily MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Tavily MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Tavily MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Tavily MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other research agents and MCP connectors. Working code, live demos, fork what fits.

SALES

Sales call prep agent

Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.

Granola

Attio

View agent

SALES

Outbound prospecting agent

Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.

Apollo

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Tavily MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Tavily MCP as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Tavily MCP api key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Tavily MCP?

Yes. Pass a tool name filter to listScopedTools so the research agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Tavily MCP.

What happens when a user revokes Tavily MCP access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Are search results cached or shared across users?

No cross-user caching. Each search uses the authorizing user's API key. Credits and rate limits apply per key. Results are never shared across tenants in the vault.

Tools your research agent reaches for on Tavily MCP, scoped per user.